universal-sentence-encoder-multilingual can not run in TextEmbedder

[istoneyou]

Have I written custom code (as opposed to using a stock example script provided in MediaPipe)

None

OS Platform and Distribution

Android 13

MediaPipe Tasks SDK version

com.google.mediapipe:tasks-text:0.20230731

Task name (e.g. Image classification, Gesture recognition etc.)

Text Embedder

Programming Language and version (e.g. C++, Python, Java)

Java

Describe the actual behavior

Error

Describe the expected behaviour

No error

Standalone code/steps you may have used to try to get what you need

I convert the universal-sentence-encoder-multilingual model(https://tfhub.dev/google/universal-sentence-encoder-multilingual/3) to tflite, and run it with the TextEmbedder API, the the below error appears:

Select TensorFlow op(s), included in the given model, is(are) not supported by this interpreter. Make sure you apply/link the Flex delegate before inference. For the Android, it can be resolved by adding "org.tensorflow:tensorflow-lite-select-tf-ops" dependency. See instructions:https://www.tensorflow.org/lite/guide/ops_select
E  Node number 0 (FlexSentencepieceOp) failed to prepare.
E  Select TensorFlow op(s), included in the given model, is(are) not supported by this interpreter. Make sure you apply/link the Flex delegate before inference. For the Android, it can be resolved by adding "org.tensorflow:tensorflow-lite-select-tf-ops" dependency. See instructions: https://www.tensorflow.org/lite/guide/ops_select
E  Node number 0 (FlexSentencepieceOp) failed to prepare.
E  E20231103 15:11:31.223073  9368 calculator_graph.cc:853] INTERNAL: CalculatorGraph::Run() failed in Run: Calculator::Open() for node "mediapipe_tasks_text_text_embedder_textembeddergraph__mediapipe_tasks_core_inferencesubgraph__inferencecalculator__mediapipe_tasks_text_text_embedder_textembeddergraph__mediapipe_tasks_core_inferencesubgraph__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:227) (interpreter->AllocateTensors())==(kTfLiteOk)
E  Text embedder failed to load model with error: internal: CalculatorGraph::Run() failed in Run: Calculator::Open() for node "mediapipe_tasks_text_text_embedder_textembeddergraph__mediapipe_tasks_core_inferencesubgraph__inferencecalculator__mediapipe_tasks_text_text_embedder_textembeddergraph__mediapipe_tasks_core_inferencesubgraph__InferenceCalculator" failed: ; RET_CHECK failure (mediapipe/calculators/tensor/inference_interpreter_delegate_runner.cc:227) (interpreter->AllocateTensors())==(kTfLiteOk)

Does the TextEmbedder API support the universal-sentence-encoder-multilingual?

Other info / Complete Logs

No response

[helpforsoftware]

same aproach and same error here. please support multilangual models